The United States has been going through a road accident crisis for many years. The National Safety Council estimates 40,000 people were killed and 4.57 million injured on U.S. roads in 2017. Direct and indirect loss from tra c congestion only is more than $140 billion every year. Vehicular Ad-hoc Networks (VANETs) are envisioned as the future of Intelligent Transportation Systems (ITSs). They have a great potential to enable all kinds of applications that will enhance road safety and transportation efficiency. In this dissertation, we have aggregated seven years of real-life tra c and incidents data, obtained from the Florida Department of Transportation District 4. We have studied and investigated the causes of road incidents by applying machine learning approaches to this aggregated big dataset. A scalable, reliable, and automatic system for predicting road incidents is an integral part of any e ective ITS. For this purpose, we propose a cloud-based system for VANET that aims at preventing or at least decreasing tra c congestions as well as crashes in real-time. We have created, tested, and validated a VANET traffic dataset by applying the connected vehicle behavioral changes to our aggregated dataset. To achieve the scalability, speed, and fault-tolerance in our developed system, we built our system in a lambda architecture fashion using Apache Spark and Spark Streaming with Kafka. We used our system in creating optimal and safe trajectories for autonomous vehicles based on the user preferences. We extended the use of our developed system in predicting the clearance time on the highway in real-time, as an important component of the traffic incident management system. We implemented the time series analysis and forecasting in our real-time system as a component for predicting traffic flow. Our system can be applied to use dedicated short communication (DSRC), cellular, or hybrid communication schema to receive streaming data and send back the safety messages. The performance of the proposed system has been extensively tested on the FAUs High Performance Computing Cluster (HPCC), as well as on a single node virtual machine. Results and findings confirm the applicability of the proposed system in predicting traffic incidents with low processing latency. / Includes bibliography. / Dissertation (Ph.D.)--Florida Atlantic University, 2018. / FAU Electronic Theses and Dissertations Collection

Worldwide, fatal traffic injuries and drowning deaths are important problems. The aim of this thesis was to investigate the cirumstances of fatal and non-fatal traffic injuries and drowning deaths in Sweden including analysis of the presence of alcohol and drugs, which are considered to be major risk factors for these events. Data where obtained from the database of National Board of Forensic Medicine. In the first study, we investigated 420 passenger deaths from 372 crashes during 1993-1996. There were 594 drivers involved. In total, 21% of the drivers at fault were alcohol positive compared to 2% of drivers not at fault (p<0.001) (Paper I). During 2004-2007, crashes involving 56 fatally and 144 non-fatally injured drivers were investigated in a prospective study from Northern Sweden (Paper II). The drivers were alcohol positive in 38% and 21%, respectively. Psychoactive drugs were found in 7% and 13%, respectively. Benzodiazepines, opiates and antidepressants were the most frequent drugs found in drivers. Illict drugs were found 9% and 4% respectively, with tetrahydrocannabinol being the most frequent of these drugs (Paper II). We investigated 5,125 drowning deaths in Sweden during 1992-2009 (Paper III). The incidence decreased on average by about 2% each year (p<0.001). Unintentional drowning was most common (50%). Alcohol was found in 44% of unintentional, 24% of intentional, and 45% of undetermined drowning deaths. Psychoactive substances were detected in 40% and benzodiazepines were the most common substance. Illicit drugs were detected in 10%. Of all drowning deaths, a significantly higher proportion females commited suicide compared with males (55% vs. 21%, p<0.001). Suicidal drowning deaths (n=129) in Northern Sweden were studied further in detail (Paper IV). of these, 53% had been hospitalized due to a psychiatric diagnosis within five years prior to the suicide. Affective and psychotic disorders were the most common psychiatric diagnoses. Almost one third had performed a previous suicide attempt. One fourth had committed suicide after less than one week of discharge from hospital. Alochol was found in 16% and psychoactive drugs in 62% of these cases, respectively.  In conclusion, alcohol and psychoactive drugs are commonly detected among injured drivers and drowning victims, and probably play a role in these events. Most of the individuals that tested positive for alcohol and high blood concentrations, indicating alochol dependence or abuse. This association warrants futher attention when planning future prevention.